Become a sponsor to Aman Priyanshu
I am Aman Priyanshu, currently pursuing my undergrad in Information Technology. My research interests include Privacy Preserving Machine Learning, Explainable AI, Fairness, and AI for Social Good. I have recently focused on areas such as Reinforcement Learning, Causal Inference, Bias Mitigation, and Low-Resource Computations. I have had the opportunity to gain practical experience through internships, including working as a Privacy Engineer Intern, a MITACS Research Intern, and a Recommendation System Intern.
I have also had the opportunity to have several publications in the field of machine intelligence and security and have won awards for my projects. My explorations in technology are also extended to participating in hackathons, where I've applied my research to developing applications aimed at social good. I intend to pursue a doctoral after my undergrad.
I'm currently working on:
- Privacy-preserving recommendation systems (specialising in resource-constrained devices)
- Explaining inference results through XAI & Causality for making neural networks more trustworthy.
- Belief networks and exploration into AI for healthcare
- Reinforcement-learning for game mechanics and multi-party/swarm intelligence
Why this sponsorship is important to me?
Being an undergrad student and an academic I'm tailored to being a monetary leak for my family. It has been a burning desire for me to explore this field of computer science especially my passions without any financial inhibitions. I'm looking for this independence through this sponsorship.
Featured work
-
AmanPriyanshu/Deep-Belief-Networks-in-PyTorch
The aim of this repository is to create RBMs, EBMs and DBNs in generalized manner, so as to allow modification and variation in model types.
Python 58 -
AmanPriyanshu/DP-HyperparamTuning
DP-HyperparamTuning offers an array of tools for fast and easy hypertuning of various hyperparameters for the DP-SGD algorithm.
Jupyter Notebook 24 -
AmanPriyanshu/FedPAQ-MNIST-implemenation
An implementation of FedPAQ using different experimental parameters. We will be looking at different variations of how, r(number of clients to be selected), t (local epochs) and s (Quantizer levels))
Python 22 -
AmanPriyanshu/Federated-Recommendation-Neural-Collaborative-Filtering
Federated Neural Collaborative Filtering (FedNCF). Neural Collaborative Filtering utilizes the flexibility, complexity, and non-linearity of Neural Network to build a recommender system. Aim to fed…
Python 32 -
AmanPriyanshu/AdaptKeyBERT
AdaptKeyBERT: keyword/keyphrase extraction with zero-shot and few-shot semi-supervised domain adaptation
Jupyter Notebook 24 -
AmanPriyanshu/DPSDV
Creating a Differential Privacy securing Synthetic Data Generation for tabular, relational and time series data.
Python 7